artifacts-builder

Pass

Audited by Gen Agent Trust Hub on Mar 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The initialization and bundling scripts (init-artifact.sh, bundle-artifact.sh) perform extensive shell operations, including system configuration, file management using cat, and stream manipulation using sed.
  • [EXTERNAL_DOWNLOADS]: The skill downloads and installs a large number of third-party dependencies from the npm registry during project setup, including the global installation of pnpm via npm install -g.
  • [COMMAND_EXECUTION]: The setup script employs node -e to programmatically parse and rewrite configuration files such as tsconfig.json and tsconfig.app.json.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the user-provided project name parameter.
  • Ingestion points: The init-artifact.sh script accepts a project name as a command-line argument which is used across multiple shell commands.
  • Boundary markers: No delimiters or isolation instructions are present to distinguish the project name from intended script commands.
  • Capability inventory: The script uses this input when calling system tools like pnpm, npm, and tar.
  • Sanitization: While the project name variable is quoted in shell scripts, it lacks comprehensive validation to prevent exploitation of parameters in the underlying tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 22, 2026, 06:11 PM
Security Audit — agent-trust-hub — artifacts-builder